{"list":"other","total":63,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1608.06993","title":"Densely Connected Convolutional Networks","created":"2016-08-25","cited_by_count":6720},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1409.4842","title":"Going Deeper with Convolutions","created":"2014-09-17","cited_by_count":4241},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1807.11164","title":"ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design","created":"2018-07-30","cited_by_count":1136},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"2103.15808","title":"CvT: Introducing Convolutions to Vision Transformers","created":"2021-03-29","cited_by_count":947},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2104.01136","title":"LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference","created":"2021-04-02","cited_by_count":475},{"id":"2103.16302","title":"Rethinking Spatial Dimensions of Vision Transformers","created":"2021-03-30","cited_by_count":361},{"id":"2202.03026","title":"Context Autoencoder for Self-Supervised Representation Learning","created":"2022-02-07","cited_by_count":297},{"id":"2103.11886","title":"DeepViT: Towards Deeper Vision Transformer","created":"2021-03-22","cited_by_count":289},{"id":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264},{"id":"2203.03884","title":"Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labels","created":"2022-03-08","cited_by_count":218},{"id":"2112.07910","title":"Decoupling Zero-Shot Semantic Segmentation","created":"2021-12-15","cited_by_count":199},{"id":"2111.11837","title":"Focal and Global Knowledge Distillation for Detectors","created":"2021-11-23","cited_by_count":142},{"id":"2203.15102","title":"Rethinking Semantic Segmentation: A Prototype View","created":"2022-03-28","cited_by_count":140},{"id":"2108.00154","title":"CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention","created":"2021-07-31","cited_by_count":139},{"id":"2207.13532","title":"Contrastive Masked Autoencoders are Stronger Vision Learners","created":"2022-07-27","cited_by_count":133},{"id":"2106.02689","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","created":"2021-06-04","cited_by_count":127},{"id":"2112.13492","title":"Vision Transformer for Small-Size Datasets","created":"2021-12-27","cited_by_count":122},{"id":"2112.10740","title":"Are Large-scale Datasets Necessary for Self-Supervised Pre-training?","created":"2021-12-20","cited_by_count":117},{"id":"2203.16768","title":"ReSTR: Convolution-free Referring Image Segmentation Using Transformers","created":"2022-03-31","cited_by_count":112},{"id":"2106.03746","title":"Efficient Training of Visual Transformers with Small Datasets","created":"2021-06-07","cited_by_count":108},{"id":"2205.03892","title":"ConvMAE: Masked Convolution Meets Masked Autoencoders","created":"2022-05-08","cited_by_count":105},{"id":"2105.11111","title":"Oriented RepPoints for Aerial Object Detection","created":"2021-05-24","cited_by_count":102},{"id":"2003.13865","title":"COVID-CT-Dataset: A CT Scan Dataset about COVID-19","created":"2020-03-30","cited_by_count":94},{"id":"2203.14335","title":"Deep Hierarchical Semantic Segmentation","created":"2022-03-27","cited_by_count":84},{"id":"2203.01452","title":"Bending Reality: Distortion-aware Transformers for Adapting to Panoramic Semantic Segmentation","created":"2022-03-02","cited_by_count":72},{"id":"2210.12843","title":"Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification","created":"2022-10-23","cited_by_count":65},{"id":"2108.09038","title":"Is it Time to Replace CNNs with Transformers for Medical Images?","created":"2021-08-20","cited_by_count":60},{"id":"2207.07116","title":"Bootstrapped Masked Autoencoders for Vision BERT Pretraining","created":"2022-07-14","cited_by_count":60},{"id":"2208.00449","title":"SdAE: Self-distillated Masked Autoencoder","created":"2022-07-31","cited_by_count":52},{"id":"2204.10437","title":"DiRA: Discriminative, Restorative, and Adversarial Learning for Self-supervised Medical Image Analysis","created":"2022-04-21","cited_by_count":48},{"id":"2205.09616","title":"Masked Image Modeling with Denoising Contrast","created":"2022-05-19","cited_by_count":45},{"id":"2203.10790","title":"ScalableViT: Rethinking the Context-oriented Generalization of Vision Transformer","created":"2022-03-21","cited_by_count":36},{"id":"2210.07240","title":"How to Train Vision Transformer on Small-scale Datasets?","created":"2022-10-13","cited_by_count":35},{"id":"2203.16897","title":"Multi-Granularity Alignment Domain Adaptation for Object Detection","created":"2022-03-31","cited_by_count":29},{"id":"2007.06712","title":"Embedded Encoder-Decoder in Convolutional Networks Towards Explainable AI","created":"2020-06-19","cited_by_count":24},{"id":"2203.15202","title":"SimT: Handling Open-set Noise for Domain Adaptive Semantic Segmentation","created":"2022-03-29","cited_by_count":17},{"id":"2203.15380","title":"SepViT: Separable Vision Transformer","created":"2022-03-29","cited_by_count":16},{"id":"2203.14043","title":"Semantic Segmentation by Early Region Proxy","created":"2022-03-26","cited_by_count":14},{"id":"2203.09093","title":"Semantic-aligned Fusion Transformer for One-shot Object Detection","created":"2022-03-17","cited_by_count":13},{"id":"2207.06985","title":"ObjectBox: From Centers to Boxes for Anchor-Free Object Detection","created":"2022-07-14","cited_by_count":12},{"id":"2207.07889","title":"You Should Look at All Objects","created":"2022-07-16","cited_by_count":12},{"id":"2210.11470","title":"i-MAE: Are Latent Representations in Masked Autoencoders Linearly Separable?","created":"2022-10-20","cited_by_count":8},{"id":"1511.05635","title":"Competitive Multi-scale Convolution","created":"2015-11-18","cited_by_count":4}],"next_cursor":null}